skill-creator

Name: skill-creator
Author: Anthropic

Create, refine, and evaluate AI skills for better performance and triggering accuracy.

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source

Summary

The material indicates an open-source, prompt-only skill with no required secrets and no declared remote endpoints, so overall risk is low. The README mentions assisting with evaluations and skill iteration, but based on the provided facts there are no concrete red flags of standalone code execution, data exfiltration, or excessive permissions.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required, and there is no indication that users must provide API tokens, account credentials, or other sensitive authentication data, so credential exposure risk is low.

Network egressLow risk

No remote endpoints are declared, and the system flags it as prompt-only; based on the available material, there is no evidence of sending user data to third-party services or unknown hosts.

Code executionLow risk

As a prompt-only skill, it does not itself appear to require local dependency installation, process spawning, or script execution. Although the README mentions evaluation scripts and runtime workflows, the current audit material does not show that this skill directly obtains code execution privileges.

Data accessLow risk

There is no declared need to read or write local files, databases, system directories, or external resources; the material suggests it mainly guides skill creation and optimization, with no sign of excessive data access requests.

Supply chainCaution

The source is an open-source GitHub repository, which supports auditability, and being from anthropics/skills is a positive trust signal; however, the license is undeclared, it has 0 stars, and maintenance status is unknown, so some supply-chain caution remains warranted.

Recommendations

Before adopting it, verify the repository license, recent commits, and issue activity.
If later versions add scripts or evaluation tools, review the actual code and network behavior first.
Before production use, validate its behavior in an isolated environment with least privilege.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "skill-creator" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md
2. Save it as ~/.claude/skills/skill-creator/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Skill Creator

A skill for creating new skills and iteratively improving them.

At a high level, the process of creating a skill goes like this:

Decide what you want the skill to do and roughly how it should do it
Write a draft of the skill
Create a few test prompts and run claude-with-access-to-the-skill on them
Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
- Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
Repeat until you're satisfied
Expand the test set and try again at larger scale

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.

On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.

Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

Cool? Cool.

Communicating with the user

The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.

So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:

"evaluation" and "benchmark" are borderline, but OK
for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them

It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.

Creating a skill

Capture Intent

Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.

What should this skill enable Claude to do?
When should this skill trigger? (what user phrases/contexts)
What's the expected output format?
Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.